## Langevin dynamics

## Metropolis-adjusted Langevin algorithm (MALA)

## Annealed

Jolicoeur-Martineau et al. (2022); Song and Ermon (2020a); Song and Ermon (2020b)

Generative Modeling by Estimating Gradients of the Data Distribution | Yang Song

## Incoming

See log concave distributions for a family of distributions where this works especially well. Rob Salomone explains this well; see Hodgkinson, Salomone, and Roosta (2019). Holden Lee, Andrej Risteski introduce the connection between log-concavity and convex optimisation.

\[ x_{t+\eta} = x_t - \eta \nabla f(x_t) + \sqrt{2\eta}\xi_t,\quad \xi_t\sim N(0,I). \]

Left-field, Max Raginsky, Sampling Using Diffusion Processes, from Langevin to Schrödinger:

the Langevin process gives only approximate samples from \(\mu\). I would like to discuss an alternative approach that uses diffusion processes to obtain exact samples in finite time. This approach is based on ideas that appeared in two papers from the 1930s by Erwin Schrödinger in the context of physics, and is now referred to as the Schrödinger bridge problem.

## References

*Proceedings of the 32nd International Conference on Neural Information Processing Systems*, 8278–88. NIPS’18. Red Hook, NY, USA: Curran Associates Inc.

*arXiv:1704.04752 [Math, Stat]*, April.

*arXiv:1605.01559 [Math, Stat]*, May.

*SIAM Journal on Applied Dynamical Systems*19 (1): 412–41.

*arXiv:1812.00793 [Cs, Math, Stat]*, September.

*Journal of the Royal Statistical Society: Series B (Statistical Methodology)*73 (2): 123–214.

*Journal of the Royal Statistical Society: Series B (Methodological)*56 (4): 549–81.

*arXiv:1903.12322 [Cs, Stat]*, March.

*arXiv:1610.00781 [Math, Stat]*, October.

*Nuclear Physics B*180 (3): 378–84.

*Statistics & Probability Letters*182 (March): 109321.

*Advances in Neural Information Processing Systems*. Vol. 28. NIPS’15. Curran Associates, Inc.

*Advances In Neural Information Processing Systems*. arXiv.

*Advances In Neural Information Processing Systems*. arXiv.

*Proceedings of the 28th International Conference on International Conference on Machine Learning*, 681–88. ICML’11. Madison, WI, USA: Omnipress.

*Statistics & Probability Letters*91 (Supplement C): 14–19.

## No comments yet. Why not leave one?